def first_neural_network(self, file, learning_rate, momentum, l2_penalty,
epoch):
'''Initializing node list, dict list and dict sibling'''
# we parse the data of the file into a tree
tree = file_parser(file)
# convert its nodes into the Node class we have, and assign their attributes
ls_nodes, dict_ast_to_Node = node_object_creator(tree)
ls_nodes = node_position_assign(ls_nodes)
ls_nodes, dict_sibling = node_sibling_assign(ls_nodes)
ls_nodes = leaves_nodes_assign(ls_nodes, dict_ast_to_Node)
# Initializing vector embeddings
embed = Embedding(self.vector_size, ls_nodes, dict_ast_to_Node)
ls_nodes = embed.node_embedding()
# Calculate the vector representation for each node
vector_representation = First_neural_network(ls_nodes,
dict_ast_to_Node,
self.vector_size,
learning_rate, momentum,
l2_penalty, epoch)
ls_nodes, w_l_code, w_r_code, b_code = vector_representation.vector_representation(
)
return [
ls_nodes, dict_ast_to_Node, dict_sibling, w_l_code, w_r_code,
b_code
]
def set_up_dynamic_pooling_layer():
tree = file_parser('test\pruebas.py')
ls_nodes, dict_ast_to_Node = node_object_creator(tree)
ls_nodes = node_position_assign(ls_nodes)
ls_nodes, dict_sibling = node_sibling_assign(ls_nodes)
embed = Embedding(20, ls_nodes, dict_ast_to_Node)
ls_nodes = embed.node_embedding()[:]
vector_representation = First_neural_network(ls_nodes, dict_ast_to_Node,
20, 0.1, 0.001)
ls_nodes, w_l, w_r, b_code = vector_representation.vector_representation()
w_comb1 = torch.diag(torch.randn(20, dtype=torch.float32)).requires_grad_()
w_comb2 = torch.diag(torch.randn(20, dtype=torch.float32)).requires_grad_()
coding_layer = Coding_layer(20, w_comb1, w_comb2)
ls_nodes = coding_layer.coding_layer(ls_nodes, dict_ast_to_Node, w_l, w_r,
b_code)
w_t = torch.randn(4, 20, requires_grad=True)
w_r = torch.randn(4, 20, requires_grad=True)
w_l = torch.randn(4, 20, requires_grad=True)
b_conv = torch.randn(4, requires_grad=True)
convolutional_layer = Convolutional_layer(20,
w_t,
w_r,
w_l,
b_conv,
features_size=4)
ls_nodes = convolutional_layer.convolutional_layer(ls_nodes,
dict_ast_to_Node)
max_pooling_layer = Max_pooling_layer()
max_pooling_layer.max_pooling(ls_nodes)
dynamic_pooling = Dynamic_pooling_layer()
hidden_input = dynamic_pooling.three_way_pooling(ls_nodes, dict_sibling)
return ls_nodes, hidden_input
def set_up_matrix():
tree = file_parser('test\pruebas.py')
ls_nodes, dict_ast_to_Node = node_object_creator(tree)
embed = Embedding(20, ls_nodes, dict_ast_to_Node)
ls_nodes = embed.node_embedding()[:]
matrices = MatrixGenerator(20, 10)
return matrices
def set_up_one_max_pooling_layer():
path = os.path.join('test', 'generators')
data = os.path.join(path, 'prueba.py')
tree = file_parser(data)
ls_nodes, dict_ast_to_Node = node_object_creator(tree)
ls_nodes = node_position_assign(ls_nodes)
ls_nodes, dict_sibling = node_sibling_assign(ls_nodes)
ls_nodes = leaves_nodes_assign(ls_nodes, dict_ast_to_Node)
ls_nodes = leaves_nodes_assign(ls_nodes, dict_ast_to_Node)
embed = Embedding(20, ls_nodes, dict_ast_to_Node)
ls_nodes = embed.node_embedding()[:]
vector_representation = First_neural_network(ls_nodes, dict_ast_to_Node,
20, 0.1, 0.001, 0, 5)
ls_nodes, w_l, w_r, b_code = vector_representation.vector_representation()
w_comb1 = torch.diag(torch.randn(20, dtype=torch.float32)).requires_grad_()
w_comb2 = torch.diag(torch.randn(20, dtype=torch.float32)).requires_grad_()
coding_layer = Coding_layer(20, w_comb1, w_comb2)
ls_nodes = coding_layer.coding_layer(ls_nodes, dict_ast_to_Node, w_l, w_r,
b_code)
w_t = torch.randn(4, 20, requires_grad=True)
w_r = torch.randn(4, 20, requires_grad=True)
w_l = torch.randn(4, 20, requires_grad=True)
b_conv = torch.randn(4, requires_grad=True)
convolutional_layer = Convolutional_layer(20,
w_t,
w_r,
w_l,
b_conv,
features_size=4)
ls_nodes = convolutional_layer.convolutional_layer(ls_nodes,
dict_ast_to_Node)
pooling_layer = Pooling_layer()
pooled_tensor = pooling_layer.pooling_layer(ls_nodes)
return pooled_tensor
def set_up_vector_representation():
tree = file_parser('test\pruebas.py')
ls_nodes, dict_ast_to_Node = node_object_creator(tree)
embed = Embedding(20, ls_nodes, dict_ast_to_Node)
ls_nodes = embed.node_embedding()[:]
vector_representation = First_neural_network(ls_nodes, dict_ast_to_Node,
20, 0.1, 0.001)
ls_nodes, w_l, w_r, b_code = vector_representation.vector_representation()
return ls_nodes, w_l, w_r, b_code
def set_up_matrix():
path = os.path.join('test', 'generators')
data = os.path.join(path, 'prueba.py')
tree = file_parser(data)
ls_nodes, dict_ast_to_Node = node_object_creator(tree)
embed = Embedding(20, ls_nodes, dict_ast_to_Node)
ls_nodes = embed.node_embedding()[:]
matrices = MatrixGenerator(20, 10)
return matrices
def set_up_vector_representation():
path = os.path.join('test', 'generators')
data = os.path.join(path, 'prueba.py')
tree = file_parser(data)
ls_nodes, dict_ast_to_Node = node_object_creator(tree)
ls_nodes = leaves_nodes_assign(ls_nodes, dict_ast_to_Node)
embed = Embedding(20, ls_nodes, dict_ast_to_Node)
ls_nodes = embed.node_embedding()[:]
vector_representation = First_neural_network(ls_nodes, dict_ast_to_Node,
20, 0.1, 0.001, 0, 5)
ls_nodes, w_l, w_r, b_code = vector_representation.vector_representation()
return ls_nodes, w_l, w_r, b_code
def set_up_coding_layer():
tree = file_parser('test\pruebas.py')
ls_nodes, dict_ast_to_Node = node_object_creator(tree)
embed = Embedding(20, ls_nodes, dict_ast_to_Node)
ls_nodes = embed.node_embedding()[:]
vector_representation = First_neural_network(ls_nodes, dict_ast_to_Node,
20, 0.1, 0.001)
ls_nodes, w_l, w_r, b_code = vector_representation.vector_representation()
w_comb1 = torch.diag(torch.randn(20, dtype=torch.float32)).requires_grad_()
w_comb2 = torch.diag(torch.randn(20, dtype=torch.float32)).requires_grad_()
coding_layer = Coding_layer(20, w_comb1, w_comb2)
ls_nodes = coding_layer.coding_layer(ls_nodes, dict_ast_to_Node, w_l, w_r,
b_code)
return ls_nodes, w_comb1, w_comb2
def set_up_coding_layer():
path = os.path.join('test', 'generators')
data = os.path.join(path, 'prueba.py')
tree = file_parser(data)
ls_nodes, dict_ast_to_Node = node_object_creator(tree)
ls_nodes = leaves_nodes_assign(ls_nodes, dict_ast_to_Node)
embed = Embedding(20, ls_nodes, dict_ast_to_Node)
ls_nodes = embed.node_embedding()[:]
vector_representation = First_neural_network(ls_nodes, dict_ast_to_Node,
20, 0.1, 0.001, 0, 5)
ls_nodes, w_l, w_r, b_code = vector_representation.vector_representation()
w_comb1 = torch.diag(torch.randn(20, dtype=torch.float32)).requires_grad_()
w_comb2 = torch.diag(torch.randn(20, dtype=torch.float32)).requires_grad_()
coding_layer = Coding_layer(20, w_comb1, w_comb2)
ls_nodes = coding_layer.coding_layer(ls_nodes, dict_ast_to_Node, w_l, w_r,
b_code)
return ls_nodes, w_comb1, w_comb2
def set_up_hidden_layer():
path = os.path.join('test', 'generators')
data = os.path.join(path, 'prueba.py')
tree = file_parser(data)
ls_nodes, dict_ast_to_Node = node_object_creator(tree)
ls_nodes = node_position_assign(ls_nodes)
ls_nodes, dict_sibling = node_sibling_assign(ls_nodes)
ls_nodes = leaves_nodes_assign(ls_nodes, dict_ast_to_Node)
embed = Embedding(20, ls_nodes, dict_ast_to_Node)
ls_nodes = embed.node_embedding()[:]
vector_representation = First_neural_network(ls_nodes, dict_ast_to_Node,
20, 0.1, 0.001, 0, 5)
ls_nodes, w_l, w_r, b_code = vector_representation.vector_representation()
w_comb1 = torch.diag(torch.randn(20, dtype=torch.float32)).requires_grad_()
w_comb2 = torch.diag(torch.randn(20, dtype=torch.float32)).requires_grad_()
coding_layer = Coding_layer(20, w_comb1, w_comb2)
ls_nodes = coding_layer.coding_layer(ls_nodes, dict_ast_to_Node, w_l, w_r,
b_code)
w_t = torch.randn(4, 20, requires_grad=True)
w_r = torch.randn(4, 20, requires_grad=True)
w_l = torch.randn(4, 20, requires_grad=True)
b_conv = torch.randn(4, requires_grad=True)
convolutional_layer = Convolutional_layer(20,
w_t,
w_r,
w_l,
b_conv,
features_size=4)
ls_nodes = convolutional_layer.convolutional_layer(ls_nodes,
dict_ast_to_Node)
max_pooling_layer = Max_pooling_layer()
max_pooling_layer.max_pooling(ls_nodes)
dynamic_pooling = Dynamic_pooling_layer()
hidden_input = dynamic_pooling.three_way_pooling(ls_nodes, dict_sibling)
w_hidden = torch.randn(3, requires_grad=True)
b_hidden = torch.randn(1, requires_grad=True)
hidden = Hidden_layer(w_hidden, b_hidden)
output_hidden = hidden.hidden_layer(hidden_input)
return output_hidden, w_hidden, b_hidden
def first_neural_network(training_dict,
vector_size=20,
learning_rate=0.1,
momentum=0.01,
l2_penalty=0,
epoch=45):
total = len(training_dict)
i = 1
for data in training_dict:
# Initializing node list, dict list and dict sibling
# we parse the data of the file into a tree
tree = file_parser(data)
# convert its nodes into the Node class we have, and assign their attributes
ls_nodes, dict_ast_to_Node = node_object_creator(tree)
ls_nodes = node_position_assign(ls_nodes)
ls_nodes, dict_sibling = node_sibling_assign(ls_nodes)
ls_nodes = leaves_nodes_assign(ls_nodes, dict_ast_to_Node)
# Initializing vector embeddings
embed = Embedding(vector_size, ls_nodes, dict_ast_to_Node)
ls_nodes = embed.node_embedding()
# Calculate the vector representation for each node
vector_representation = First_neural_network(ls_nodes,
dict_ast_to_Node,
vector_size,
learning_rate, momentum,
l2_penalty, epoch)
ls_nodes, w_l_code, w_r_code, b_code = vector_representation.vector_representation(
)
training_dict[data] = [
ls_nodes, dict_ast_to_Node, dict_sibling, w_l_code, w_r_code,
b_code
]
print(f"finished vector representation of file: {data} ({i}/{total})")
i += 1
return training_dict
